基于DWT与HMM的纸币图像分类方法

Banknote Image Classification Method Combining DWT with HMM

针对纸币图像退化造成纸币图像识别率下降的问题,提出了一种基于小波变换(DWT)与隐马尔科夫模型(HMM)的实时纸币图像分类方法:首先对纸币图像进行预处理,然后运用DWT提取纸币图像的纹理特征信息,最后运用HMM对纸币图像进行分类。通过对人民币等不同币种进行实验,证明了该方法能有效地克服纸币图像退化对识别率的影响,具有较高的识别率与稳定性。

According to the problem of decreased recognition rate by the degradation of the banknote image,a real time banknote image classification method based on hidden markov models is presented in this paper.Firstly,the proposed method is used to preprocess the banknote image,and then wavelet transform is applied to extract the texture characteristics of banknote.At last,hidden markov model is used to classify the banknote image.In order to verify the validity of the proposed method,the experiments are conducted on different banknotes.The experimental results show that the proposed method overcomes the influence of banknote image degradation on the recognition rate and obtains high recognition rate and high stability.